Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15375
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, likely named "Gaud"

    oai_token-act-pair · gpt-3.5-turbo

    references to auditory elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LINE
    -0.67
     Helsinki
    -0.65
     MET
    -0.65
     Dani
    -0.62
     sol
    -0.61
     bis
    -0.61
    ANE
    -0.60
     patience
    -0.60
     turtle
    -0.59
     retard
    -0.58
    POSITIVE LOGITS
    oin
    1.18
    din
    1.04
    alties
    0.97
    iences
    0.95
    ience
    0.94
    ible
    0.89
    yssey
    0.85
    deen
    0.84
    enos
    0.84
    reau
    0.83
    Activations Density 0.023%

    No Known Activations